← Back to community benchmarks
Qwen3.5-122B-A10B
Performance
16k
tokens
532.6
PP tok/s
32.5
TG tok/s
30761
TTFT (ms)
98.1
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.24
macOS
macOS 26.4
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 532.4 | 38.3 | 94.9 GB | view |
| 4k | 577.1 | 37.0 | 96.3 GB | view |
| 8k | 564.8 | 35.7 | 96.9 GB | view |
| 16k | 532.6 | 32.5 | 98.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.3 | 1.00× |
| 2× | 56.5 | 1.48× |
| 4× | 70.1 | 1.83× |